We present a system for designing and displaying grid-based document designs that adapt to many different viewing conditions and content selections. Our system can display traditional, static documents, or it can assemble dynamic documents "on the fly" from many disparate sources via the Internet. Our adaptive layouts for aggregated documents are inspired by traditional newspaper design. Furthermore, our system allows documents to be interactive so that readers can customize documents as they read them. Our system builds on previous work on adaptive documents, using constraint-based templates to specify content-independent page designs. The new templates we describe are much more flexible in their ability to adapt to different types of content and viewing situations. This flexibility comes from allowing the individual components, or "elements," of the templates to be mixed and matched, according to the content being displayed. We demonstrate our system with two example applications: an interactive news reader for the New York Times, and an Internet news aggregator based on MSN Newsbot.

Cheap and versatile cameras make it possible to easily and quickly capture a wide variety of documents. However, low resolution cameras present a challenge to OCR because it is virtually impossible to do character segmentation independently from recognition. In this paper we solve these problems simultaneously by applying methods borrowed from cursive handwriting recognition. To achieve maximum robustness, we use a machine learning approach based on a convolutional neural network. When our system is combined with a language model using dynamic programming, the overall performance is in the vicinity of 80-95% word accuracy on pages captured with a 1024/spl times/768 webcam and 10-point text.

Grid-based page designs are ubiquitous in commercially printed publications, such as newspapers and magazines. Yet, to date, no one has invented a good way to easily and automatically adapt such designs to arbitrarily-sized electronic displays. The difficulty of generalizing grid-based designs explains the generally inferior nature of on-screen layouts when compared to their printed counterparts, and is arguably one of the greatest remaining impediments to creating on-line reading experiences that rival those of ink on paper. In this work, we present a new approach to adaptive grid-based document layout, which attempts to bridge this gap. In our approach, an adaptive layout style is encoded as a set of grid-based templates that know how to adapt to a range of page sizes and other viewing conditions. These templates include various types of layout elements (such as text, figures, etc.) and define, through constraint-based relationships, just how these elements are to be laid out together as a function of both the properties of the content itself, such as a figure's size and aspect ratio, and the properties of the viewing conditions under which the content is being displayed. We describe an XML-based representation for our templates and content, which maintains a clean separation between the two. We also describe the various parts of our research prototype system: a layout engine for formatting the page; a paginator for determining a globally optimal allocation of content amongst the pages, as well as an optimal pairing of templates with content; and a graphical user interface for interactively creating adaptive templates. We also provide numerous examples demonstrating the capabilities of this prototype, including this paper, itself, which has been laid out with our system.

This paper describes a new framework for processing images by example, called “image analogies.” The framework involves two stages: a design phase, in which a pair of images, with one image purported to be a “filtered” version of the other, is presented as “training data”; and an application phase, in which the learned filter is applied to some new target image in order to create an “analogous” filtered result. Image analogies are based on a simple multi-scale autoregression, inspired primarily by recent results in texture synthesis. By choosing different types of source image pairs as input, the framework supports a wide variety of “image filter” effects, including traditional image filters, such as blurring or embossing; improved texture synthesis, in which some textures are synthesized with higher quality than by previous approaches; super-resolution, in which a higher-resolution image is inferred from a low-resolution source; texture transfer, in which images are “texturized” with some arbitrary source texture; artistic filters, in which various drawing and painting styles are synthesized based on scanned real-world examples; and texture-by-numbers, in which realistic scenes, composed of a variety of textures, are created using a simple painting interface.

We present a new representation for time-varying image data that allows for varying-and arbitrarily high-spatial and temporal resolutions in different parts of a video sequence.The representation, called multiresolution video, is based on a sparse, hierarchical encoding of the video data.We describe a number of operations for creating, viewing, and editing multiresolution sequences.These operations support a variety of applications: multiresolution playback, including motion-blurred "fast-forward" and "reverse"; constantspeed display; enhanced video scrubbing; and "video clip-art" editing and compositing.The multiresolution representation requires little storage overhead, and the algorithms using the representation are both simple and efficient.

We present a method for searching in an image database using a query image that is similar to the intended target.The query image may be a hand-drawn sketch or a (potentially low-quality) scan of the image to be retrieved.Our searching algorithm makes use of multiresolution wavelet decompositions of the query and database images.The coefficients of these decompositions are distilled into small "signatures" for each image.We introduce an "image querying metric" that operates on these signatures.This metric essentially compares how many significant wavelet coefficients the query has in common with potential targets.The metric includes parameters that can be tuned, using a statistical analysis, to accommodate the kinds of image distortions found in different types of image queries.The resulting algorithm is simple, requires very little storage overhead for the database of signatures, and is fast enough to be performed on a database of 20,000 images at interactive rates (on standard desktop machines) as a query is sketched.Our experiments with hundreds of queries in databases of 1000 and 20,000 images show dramatic improvement, in both speed and success rate, over using a conventional L 1 , L 2 , or color histogram norm.